Auto-Lithology Identification Based on KNN

Abstract:

Accurately grasping the distribution of different rocks can achieve the minimum explosive consumption and meet with the requirements of blasting quality; Not only reduces the cost of blasting, but also improves the safety and controllability of blasting. By utilizing the physical reactions to different rocks in the rigs process, the manual assisted learning process of the rig and the two stages of automatic drilling are proposed; After the automatic drilling, the lithology distribution of the borehole can be obtained in real time. The automatic drilling is the key to achieving fine blasting. Combined with the research of specific rigs and data processing methods. A KNN recognition model is established to construct the relationship between various indicators and lithology under certain confidence conditions, and this method can achieve automatic real-time adjustment and control of drilling parameters.

• Periodical: Advances in Science and Technology (Volume 166)
• Pages: 141-148
• DOI: https://doi.org/10.4028/p-YmHmA5
• Online since: June 2025
• Authors: Wen Xin Ji, Wei Dai*, Kun Lin Zhang, Xin Ping Han
• Keywords: Auto-Lithology, Drilling, KNN, Rock Type, Self-Learning

References

[1] Fu Guangming, Yan Jiayong, Zhang Kun et. Status and Progress of Lithological Identification Technology[J]. Progress in Geophysics | Prog Geophys, 2017, 32(1)p.26

[2] Huang Pingping. Rock Blastability Classification with Fuzzy Synthesis[J]. Quarterly Journal of Changsha Institute of Mining and Research, 1989, 9(4)p.63

[3] Yu Yalun, Wang Desheng, Qu Shijie. owning of the Blasting Compliance of Rocks in Shuichang Open Pit[J]. Chinese Journal of Rock Mechanics and Engineering, 1990, 9(3)p.195

[4] He Gongzhuo, Zou Xueqin. A Zoning Gary Model of Blastability of Ore and Rock IN Dong'anshan Iron Mine and Its Application[J]. China Mining Magazine, 1993, 2(5)p.27

[5] K. Wang, Y. Liu, P. Li. Recognition method of drilling conditions based on support vector machine[C]//2022 ICPECA, Shenyang, China, 2022: 233-237.

DOI: 10.1109/icpeca53709.2022.9718844

[6] Alghandoor A, Phelan P E, Villalobos R, et al. U.S. manufacturing aggregate energy intensity decomposition: The application of multivariate regression analysis[J]. International Journal of Energy Research, 2010, 32(2)p.91

DOI: 10.1002/er.1334

[7] Wu Chong. Research on the Acquisition and Application of Drilling Parameters of Rotary Drilling Rigs in Open Pit Mines[D]. Liaoning Technical University. 2015.

[8] Feng Panxue, Yang Zhiqiang. Application of Precise Digital Blasting Process Modeling and Effect Evaluation[J]. Non-ferrous Metals (Mining Component).2014, 66(2)p.4

[9] Ji Changpeng, Na Zhongwu, Zhang Zhengcheng, etc. A Lithology Recognition Method Based on Mining Drilling Rigs[C]//Proceedings of the China Intelligent Demolition Forum. 2018.

[10] Victor, C.G. Rock Drillability Index[M]. Beijing: China Coal Industry Publishing House. 1980.

[11] I.А. Tangayev, Drillability and Explosivity of Rock[M]. Beijing: Metallurgical Industry Press. 1987.

[12] Zhou Zhihua. Machine Learning[M], Beijing: Tsinghua University publishing Press. 2016.

[13] P. Zhao, L. Lai. Analysis of KNN Density Estimation[J]. IEEE Transactions on Information Theory, 2022, 68(12)p.7971

DOI: 10.1109/tit.2022.3195870

[14] Lusiola T. Synthesis and processing of KNN powders and thick films for MEMS devices[D]. Cranfield university, 2012.